{"id":"W4403785816","doi":"10.1016/j.joi.2025.101759","title":"WISDOM: An AI-powered framework for emerging research detection using weak signal analysis and advanced topic modelling","year":2025,"lang":"en","type":"preprint","venue":"Journal of Informetrics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"","keywords":"SIGNAL (programming language); Computer science; Detection theory; Data science; Artificial intelligence; Telecommunications","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007704637,0.0001664131,0.0006253293,0.005751865,0.0008310779,0.000387283,0.0004135058,0.0003780236,0.00003156775],"category_scores_gemma":[0.002683722,0.0001596586,0.0005133205,0.006618628,0.0001184427,0.0005237653,0.000188367,0.001276822,1.679012e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004461727,"about_ca_system_score_gemma":0.0009119769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000648601,"about_ca_topic_score_gemma":0.0002760284,"domain_scores_codex":[0.9968462,0.0004199026,0.0009273671,0.0002457316,0.001211951,0.0003488587],"domain_scores_gemma":[0.9933202,0.002547074,0.0008883469,0.0001662364,0.002880689,0.0001974642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001003891,0.00004061509,0.001198726,0.00008453961,0.0007870835,0.000001584073,0.002898043,0.7103825,0.0000129596,0.006186138,0.000004254869,0.2783031],"study_design_scores_gemma":[0.0002325872,0.0001175691,0.0003491975,0.0001709534,0.0009585069,0.000001270667,0.003297678,0.7764993,0.00007948073,0.2151358,0.002951028,0.0002066508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08964142,0.0009882273,0.907922,0.0002107655,0.0005198701,0.0002032529,0.000008299594,0.0000107223,0.0004953926],"genre_scores_gemma":[0.540474,0.00100559,0.4576967,0.00004039083,0.0006249686,0.000004754776,0.000005544962,0.000007555582,0.0001405061],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4508326,"threshold_uncertainty_score":0.651069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2034003105124179,"score_gpt":0.525670070531794,"score_spread":0.3222697600193761,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}